Qwen-Image-2.1-DiT-NVFP4-ComfyUINEWby pottokaoβ‘ CPU/GPUβ¬ 0β₯ 0text-to-imageImageotherlicense:otherView on Hugging Face
nemotron3-nano-30b-a3b-2p03bit-r22NEWby minjaechoiπ₯οΈ GPUFP16~72 GB30B paramsβ¬ 0β₯ 0text-generationLanguageotherconversationaldataset:nvidia/nemotron-cc-v2dataset:nvidia/nemotron-cc-math-v1dataset:nvidia/nemotron-cc-v2.1View on Hugging Face
LFM2-1.2B-Longevity-4bit-mlxNEWby OpenMedπ» CPUMLX~1 GB1.2B paramsβ¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face
LFM2-1.2B-Longevity-8bit-mlxNEWby OpenMedπ» CPUMLX~1 GB1.2B paramsβ¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face
Jarvis-0.5BNEWby spooks010π» CPUGGUF~1 GB500M paramsβ¬ 0β₯ 0text-generationLanguageotherconversationaldataset:abhaykoul/jarvislicense:otherView on Hugging Face
Swift-Qwen3.8-27B-MLX-3bitNEWby majentikπ» CPUMLX~17 GB27B paramsβ¬ 0β₯ 0OtherView on Hugging Face
LFM2-2.6B-Longevity-4bit-mlxNEWby OpenMedπ» CPUMLX~2 GB2.6B paramsβ¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face
train_800_dense__point__overlay_a25__sim__all_cameras__live__pi05__seed_0NEWby mim-chess-vlasπ₯οΈ GPUFP16β¬ 0β₯ 0OtherView on Hugging Face
LFM2-2.6B-Longevity-8bit-mlxNEWby OpenMedπ» CPUMLX~2 GB2.6B paramsβ¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face